Contrastive Self-Supervised Learning and Potential Limitations - Dr Ting Chen from Google Brain

Abstract: Contrastive learning has achieved some impressive results recently for learning visual representations from images without human supervision. As an example, SimCLR (and many other subsequent work) is able to learn representations that rival or outperform supervised learning on ImageNet without using any labels. In this talk, I will cover a few topics on contrastive self-supervised learning, including an overview of a few basic contrastive methods, important factors in contrastive learning, simple approaches for semi-supervised learning (with lots of unlabeled images and a few labeled images), some intriguing properties and potential limitations of existing contrastive learning methods. Bio: Dr Ting Chen joined Google Brain in 2019 as a Research Scientist. On March 2019, he received his Ph.D. degree from Department of Computer Science at UCLA. His research interests are in Self-Supervised Learning, Generative Modelling, and Discrete Structures and Efficient Modeling.